Our machine overlords have come for our movie industry

[P3nT4gR4m]

Refer to conspiracy theory above - video was deleted so we couldn't reverse engineer it to find a cure for the mind control virus. Virus will now propagate in benign form, from the people who saw it to the people they interact with. Eventually, everyone will be infected and an activation signal will be broadcast.

[The Wizard Joseph]

Refer to conspiracy theory above - video was deleted so we couldn't reverse engineer it to find a cure for the mind control virus. Virus will now propagate in benign form, from the people who saw it to the people they interact with. Eventually, everyone will be infected and an activation signal will be broadcast.

I do feel kinda peculiar ever since watching it...

[Pæs]

Author of it wrote this: https://medium.com/@rossgoodwin/adventures-in-narrated-reality-6516ff395ba3#.pbwxlaagf and Part II seems to deal with that video in the OP, however from what I gather the URL to the draft version was leaked before intended release, so it was taken down temporarily.

[Prelate Diogenes Shandor]

Is the video anywhere else?

[axod]

This just in - for possible (not OP) video application.  From Nvidia:

Researchers from University of Freiburg in Germany are using cuDNN deep learning software and NVIDIA TITAN X GPUs to extract a specific artistic style from a source painting, and then synthesizes this information with the content of a separate video.

The team builds upon previous work of applying artistic styles to images – but extending this technique for videos is more challenging.

“If you just apply the algorithm frame by frame, you don’t get a coherent video — you get flickering in the sequence,” says University of Freiburg postdoc Alexey Dosovitskiy. “What we do is introduce additional constraints, which make the video consistent.”

- See more at: https://news.developer.nvidia.com/deep-learning-helps-transfer-famous-artistic-styles-to-videos/#sthash.ESTVueK4.dpuf

Video demonstration:
https://www.youtube.com/watch?v=Uxax5EKg0zA

[Vanadium Gryllz]

This just in - for possible (not OP) video application.  From Nvidia:

Researchers from University of Freiburg in Germany are using cuDNN deep learning software and NVIDIA TITAN X GPUs to extract a specific artistic style from a source painting, and then synthesizes this information with the content of a separate video.

The team builds upon previous work of applying artistic styles to images – but extending this technique for videos is more challenging.

“If you just apply the algorithm frame by frame, you don’t get a coherent video — you get flickering in the sequence,” says University of Freiburg postdoc Alexey Dosovitskiy. “What we do is introduce additional constraints, which make the video consistent.”

- See more at: https://news.developer.nvidia.com/deep-learning-helps-transfer-famous-artistic-styles-to-videos/#sthash.ESTVueK4.dpuf

Video demonstration:
https://www.youtube.com/watch?v=Uxax5EKg0zA

"Such great progress in so little time."

That's pretty impressive. The things that people are doing with this tech that they aren't putting on youtube are interesting I bet.

The robots are just about away from being able to recognise and categorise objects in real time.

Robot apocalypse is back on?

[The Wizard Joseph]

Certainly going to be a major feature in all future eschatonic scenarios.

(Wizard looks to the left and takes the tablet from his eyes)

I don't know about that.

(Tablet drops, breaking the floor in the sky)

[Brother Mythos]

This just in - for possible (not OP) video application.  From Nvidia:

Researchers from University of Freiburg in Germany are using cuDNN deep learning software and NVIDIA TITAN X GPUs to extract a specific artistic style from a source painting, and then synthesizes this information with the content of a separate video.

The team builds upon previous work of applying artistic styles to images – but extending this technique for videos is more challenging.

“If you just apply the algorithm frame by frame, you don’t get a coherent video — you get flickering in the sequence,” says University of Freiburg postdoc Alexey Dosovitskiy. “What we do is introduce additional constraints, which make the video consistent.”

- See more at: https://news.developer.nvidia.com/deep-learning-helps-transfer-famous-artistic-styles-to-videos/#sthash.ESTVueK4.dpuf

Video demonstration:
https://www.youtube.com/watch?v=Uxax5EKg0zA

This YouTube video is really impressive. Thanks for posting it.

[Template]

They're saying it wrote the script but I'm guessing it wrote the dialogue. I've read tons of movie scripts and dialogue is probably about 10% of most of them, the lions share being scene and action description and even camera and lighting direction in some. There was a link to the PDF of the script in the article I found this on but it was 404ing last night. I'd be interested to see it, tho.

Well, shit's being pulled but this article clarifies that the program wrote dialogue and described actions:
http://www.nerdcore.de/2016/05/20/sunspring-shortfilm-from-algorithmic-script/
https://archive.is/2zERM

    On watching the film, many of my friends did not realize that the action descriptions as well as the dialogue were computer generated. After examining the output from the computer, the production team made an effort to choose only action descriptions that realistically could be filmed, although the sequences themselves remained bizarre and surreal. The actors and production team’s interpretations and realizations of the computer’s descriptions was a fascinating case of human-machine collaboration.

    For example, here is the stage direction that led to Middleditch’s character vomiting an eyeball early in the film:
    C (smiles): I don’t know anything about any of this.
    H (to Hauk, taking his eyes from his mouth): Then what?
    H2: There’s no answer.

Likewise, the video URL if access ever comes again:
vimeo.com/163231976

[Template]

Doubleposting now that the film is online again.
thescene.com/watch/arstechnica/sunspring-sci-fi-short-film
youtube.com/watch?v=LY7x2Ihqjmc